Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    years in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.53
    2
    0.42
     "
    0.39
    1
    0.38
     T
    0.36
     think
    0.36
     The
    0.35
     Time
    0.35
     be
    0.34
    (
    0.34
    POSITIVE LOGITS
    <unused95>
    0.39
     ouvrage
    0.39
    🕉
    0.38
     veineux
    0.37
    疸
    0.37
    堊
    0.36
     أهل
    0.35
    <unused82>
    0.34
     moieties
    0.34
     کیشن
    0.34
    Act Density 0.001%

    No Known Activations